Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "tensorflow again"
-
Ok friends let's try to compile Flownet2 with Torch. It's made by NVIDIA themselves so there won't be any problem at all with dependencies right?????? /s
Let's use Deep Learning AMI with a K80 on AWS, totally updated and ready to go super great always works with everything else.
> CUDA error
> CuDNN version mismatch
> CUDA versions overwrite
> Library paths not updated ever
> Torch 0.4.1 doesn't work so have to go back to Torch 0.4
> Flownet doesn't compile, get bunch of CUDA errors piece of shit code
> online forums have lots of questions and 0 answers
> Decide to skip straight to vid2vid
> More cuda errors
> Can't compile the fucking 2d kernel
> Through some act of God reinstalling cuda and CuDNN, manage to finally compile Flownet2
> Try running
> "Kernel image" error
> excusemewhatthefuck.jpg
> Try without a label map because fuck it the instructions and flags they gave are basically guaranteed not to work, it's fucking Nvidia amirite
> Enormous fucking CUDA error and Torch error, makes no sense, online no one agrees and 0 answers again
> Try again but this time on a clean machine
> Still no go
> Last resort, use the docker image they themselves provided of flownet
> Same fucking error
> While in the process of debugging, realize my training image set is also bound to have bad results because "directly concatenating" images together as they claim in the paper actually has horrible results, and the network doesn't accept 6 channel input no matter what, so the only way to get around this is to make 2 images (3 * 2 = 6 quick maths)
> Fix my training data, fuck Nvidia dude who gave me wrong info
> Try again
> Same fucking errors
> Doesn't give nay helpful information, just spits out a bunch of fucking memory addresses and long function names from the CUDA core
> Try reinstalling and then making a basic torch network, works perfectly fine
> FINALLY.png
> Setup vid2vid and flownet again
> SAME FUCKING ERROR
> Try to build the entire network in tensorflow
> CUDA error
> CuDNN version mismatch
> Doesn't work with TF
> HAVE TO FUCKING DOWNGEADE DRIVERS TOO
> TF doesn't support latest cuda because no one in the ML community can be bothered to support anything other than their own machine
> After setting up everything again, realize have no space left on 75gb machine
> Try torch again, hoping that the entire change will fix things
At this point I'll leave a space so you can try to guess what happened next before seeing the result.
Ready?
3
2
1
> SAME FUCKING ERROR
In conclusion, NVIDIA is a fucking piece of shit that can't make their own libraries compatible with themselves, and can't be fucked to write instructions that actually work.
If anyone has vid2vid working or has gotten around the kernel image error for AWS K80s please throw me a lifeline, in exchange you can have my soul or what little is left of it5 -
*My friend texting me*
Friend: wtf
My brain: w tf
My brain again: tf
My brain again: import tensorflow as tf
😂😂am brain dead3 -
Why am I such an average ?
It's just a sad realisation. Nobody cares but I wanna send this out there, just to write thoughts.. I am 18 in 3rd year of high school (grammar school so nothing IT related, basically waste of time) and in IT I'm all self taught but I feel like I could be better if I just didn't [something]..
I feel like I wanna learn so many things but when I look at you, it seems like a common problem in the IT sphere so hey, average guy joining the club.
I also feel dumb when programming. I didn't manage to learn C++ in it's entirety because to really accomplish something, you've got so many ways to do it and finding the best one requires deep understanding of the tools you've got at your disposal with the language and I feel like I'm not capable of this(self learn, in school/Uni that's different story).. But many (most) of you are. I've tried many coding challenges and when I got it working, I just saw how someone did it in one line just by layering functions that I've never heard of..
Also, we've got kinda specific national competition here in many fields including IT for high schools.. And the winners always do sometimes like "AI driven Life simulation" or "Self flying drone made from ATMega from scratch with 3D simulation in C# to it" or "Game engine" or whatever shit and it's always from grammar schools and never IT related schools.. They are like me. Maybe someone helped them, I don't know, but they are just so far away from me while I'm here struggling to get the basic level of math for any kind of machine learning..
Yeah I've written Neural Network from scratch in C but meh, honestly it's pretty basic stuff .. I'd rather understand derivatives which we're going to learn next year and I'm too lazy to learn it from khan academy because I always learn something else.. Like processing (actually codetrain started teaching tensorflow so that might be the light for me...) Or VHDL (guys you can create your own chip / CPU from scratch and it's not even hard and OMFG it's so fucking cool , full adder done yay) or RPi or commodore 64 assembly or game development with Godot and just meh..
I mean, this sounds exactly like not knowing what to do and doing nothing in the end. That was me like 6-12 months ago. Now I'm managing to pick 2-3 things and focus them and actually feel the progress.
But I lost track of the original point.. I didn't do anything special, every time I'm programming something, everyone does it better and I feel dumb. I will probably never do anything special, everyone around says "He's still learning he's genius" but they have no idea.
I mean, have you seen one of the newest videos on Google's YouTube channel (I openly hate them, but I will keep that away for now), something like "Sarah story" ? It's about girl that apparently didn't care about IT but self learned tensorflow on high school. I think it may be bullshit (like ALL of their videos ) but it's probably just fancied, not complete lie.
And again, here I am. I now C but I'm incapable of learning to program good which most of you did and are now doing for living. I'm incapable to do anything cool, just understanding what everybody else did and replicating it. I'm incapable of being clever.
Sorry, just misusing devrant to vent a bit17 -
Waking up and guess the first item on my feed?
IBM research just released Snap ML framework that's supposedly 47x faster than Tensorflow. Now, i like advancements but fuck i just finished developing my Tensorflow model, and i don't want to rewrite this stuff again!2 -
It's not a real dev regret but it's related to it: Not being able to fix a price or a value for my skills.
It's a real regret.
Just coming out of college I have tried my hand at freelancing at found it real hard to fix a value for what work was offered because I just found it weird to fix a monetary value on something that I've done for free for my entire life ( at school and uni I mean).
To make it worse my first experience was with a grad student who wanted me to complete her project.
Now being from India, I know that we have a stereotype of doing work for a lower price.
But this girl took the cake.
She wanted me to create a custom Image classifier using tensorflow.
It had to train with live images and then detect those images in the live video feed.
It's quite simple but still training the basic network(which would be used to just detect features) would take a decent amount of time and effort.
No pre trained models was also a prerequisite for her.
After hearing all her requirements I asked her what price she was willing to pay.
She said 50$ lump sum.
Being really confused as to what to say to that I just stopped replying.
To this day I have no clue what would be a reasonable price to quote a client like that.
After that I just continued dealing with people I knew personally and am currently doing that as an internship. But entering the proper freelancing system again has become a kinda weird thing in my head now, since I have no clue as to what price to put on my skills.
Is there any advice that any of the more experienced people would give?
Also consider the fact that I'm relatively fresh out of college and have no corporate experience.
Even if you've read my rant and have no advice it's okay. I guess this is a path of self realization after all.3